• 한국IT서비스학회지
• /
• 제6권2호
• /
• pp.1-18
• /
• 2007

Many researches have been done in insurance fraud as the amount and frequency of insurance fraud have been increasing continuously. In particular, the development of insurance fraud detection system using large database management techniques including data mining or link analysis based on visual method have been the main research topic in insurance fraud. However, this kinds of detection system were very ineffective to find unintentional insurance fraud happened by accident even though it was so good to find intentional and organized crime insurance fraud. Therefore, this research suggests insurance fraud as an ethical decision making and applies TPB(Theory of Planned Behavior) for the finding of reasons and prevention strategies of unintentional insurance fraud happened by accident. The results of research show that TPB is very appropriate model to explain the behavior of insurance fraud and that insurance agents force to do insurance fraud as affecting perceived behavior control. Therefore, education and pubic relations for insurance fraud are very effective for preventing insurance fraud and developing insurance service industry.

• 한국컴퓨터정보학회논문지
• /
• 제24권1호
• /
• pp.207-215
• /
• 2019

The insurance system is indispensable to our society. However in recent years, there have been a lot of insurance fraud crimes, such as the abuse of these valuable insurance system and the cheating the insurance proceeds. These insurance frauds make the insurance companies harder to manage, and as a result, the insurance premiums have risen, which has caused a lot of damaging good policyholders. However, the damage caused by insurance fraud has been continuously increasing due to the punishment of cotton stick. Therefore, after the long discussion, the 'The Act for Prevention of Insurance Fraud', which is a special law recently has been enacted. However, within two years of the enactment of this law, which was enacted after much anticipation and long waiting, there is already debate about its effectiveness. The reason for this is that even though the law was enacted and enforced, insurance fraud continues to increase and even punishment for these crimes is not strengthened, and now it is time to look for specific problems and resolutions for these crimes see. So in this paper the author dealt with the problems of the law, first, related regulation of insurance payment, second, right to terminate insurance contract and return of insurance proceeds, third, regulation on notification of investigations, fourth, regulations on the adequacy of hospitalization. Of course, since this law has just been enacted, there are many other problems besides these problems, but I tried to present a fresh resolution based on the problems that have been mainly discussed since the legislative period.

• 경영정보학연구
• /
• 제5권1호
• /
• pp.49-60
• /
• 2003

본 연구의 목적은 현재 심각한 사회 및 경제 문제로 대두되고 있는 보험사기를 효과적으로 적발하기 위하여, visualization 데이터마이닝 tool을 실제 사례에 적용하여 그 타당성을 검증하는데 있다. 이를 위하여 최근 가장 효과적인 visualization 데이터마이닝 tool로 인정되고 있는 i2사의 Analyst's Notebook을 활용하여 대량의 보험금 청구 자료로부터 보험사기의 혐의가 가는 거래를 찾고, 이를 근거로 보첩사기의 혐의를 입증하는 일련의 과정을 검토하였다. 그 결과 visualization 데이터마이닝 tool이 대량의 보험금 청구 자료에서 혐의가 가는 거래를 찾는 단순한 예측의 수준을 넘어, 관련 범죄를 추적하여 체계적, 계획적으로 기획된 보험사기단을 추적해내는 성과를 올렸다. 따라서 보험사기 둥과 같은 부정거래나 범죄 행위를 적발하는 데는 visualization 데이터마이닝 tool이적합한 것으로 판명되었다.

• 한국컴퓨터정보학회논문지
• /
• 제25권3호
• /
• pp.117-127
• /
• 2020

최근 보험사기는 의료인, 정비업체, 보험설계사 등 분야별 전문가와 보험가입자가 공모하여 조직화, 지능화되는 형태로 계획적이고 은밀하게 이루어지고 있어 그 혐의를 입증하는 것이 점점 더 어려워지고 있다. 자동차사고의 경우 고의를 입증하기가 쉽지 않으며 특히 수사권이 없는 보험사가 혐의를 입증하기는 현실적으로 한계를 가지고 있다. 본 논문에서는 공모형 보험사기 적발을 위한 Social Network Analysis(SNA), 혐의그룹 개체간 관계 시각화 기법 등 공모형 보험사기 혐의자 적발 기법을 통해 기존에는 알아내기 어려웠던 조직형, 공모형 보험사기 파악이 획기적으로 개선될 수 있다는 점을 살펴보고 조직적 공모형 보험사기 적발을 위한 데이터 분석기법의 발전적 연구 방향을 모색해 보고자 한다.

• 의료법학
• /
• 제14권2호
• /
• pp.11-41
• /
• 2013

Article 347 of criminal law provides the act of deceiving another, thereby taking property or obtaining pecuniary advantage from another. On the other hand, the concepts of fraud and abuse are confused upon interpretation since the definition in National Healthcare Insurance Law is unclear, and it affects closely to the administrative measures such as surcharge levy by the period of inspection, therefore, the disputes continue in the forms of formal objection, administrative ruling and administrative litigation. This study aims to look over the legal problems on application of criminal fraud toward the abuse of 'Paid Medical Expenses(Article 57, Sections 1 and 4 of the National Health Insurance Act)'. The main issues are concept of abuse(Article 57, Sections 1 and 4 of the National Health Insurance Act), the problems of Directions of Health-Welfare Ministry on aspect of 'Nullum crimen sine lege' Principles, the proper sentenc-ing guidelines of fraud.

• 융합정보논문지
• /
• 제11권6호
• /
• pp.270-281
• /
• 2021

정보기술의 발달로 보험사기의 규모는 매년 급증하고 있고, 그 방법도 공모 형태로 조직화되고 고도화되고 있다. 이를 예측하고 검출하기 위한 다양한 형태의 예측모델이 연구되고 있지만 보험관련 정보는 매우 민감하여 공유와 접근에 위험이 높고 법적인 혹은 기술적인 제약이 많다. 이 논문에서는 최근 4차 산업 혁명의 등장으로 가장 각광받는 기술 중 하나인 블록체인을 기반으로 한 기계학습 보험사기 예측모델을 제안한다. 블록체인 기술을 활용하여 안전하고 신뢰받는 보험청구 정보 공유시스템을 실현하고, 보다 효율적이고 정확한 사기예측을 위하여 사회관계분석이론을 적용하여 각 관계에 가중치를 부여하고 기계학습 사기 예측패턴을 4단계로 나누어 제안하였다. 사기 가능성이 높은 보험청구건은 보다 앞선 단계에서 높은 예측 율로 검출되는 효과를 가지며 가능성이 낮은 청구 건은 사후에 참고하여 관리할 수 있도록 차등 적용하였다. 제안하는 모델의 중요 매커니즘은 이더리움(Ethereum) 로컬 네트워크를 구성하여 검증 하였고, 향후 보다 정교한 성능평가가 요구된다.

• 무역상무연구
• /
• 제67권
• /
• pp.119-142
• /
• 2015

Many insurers have traditionally incorporated "fraud clauses" into insurance policies, setting out the consequences of making a fraudulent claim. Even in the absence of an express terms, English courts provide insurers with a remedy for a fraudulent claim. However, the law in this area is complex, convoluted and confused. English Law Commission think that the law in this area needs to be reformed for three reasons; (1) the disjunctive between the common law rule and section 17 generates unnecessary disputes and litigation, (2) increasingly, UK commercial law must be justified to an international insurance society, and (3) the rules on fraudulent claims are functioned as a deterrent if they are clear and well-understood. In order for these purposes, English Law Commission recommends a statutory regime to the effect that, when an insured commits fraud in relation to a claim, the insurer should (1) have no liability to pay the fraudulent claim and be able to recover any sums already paid in respect to the claim, and (2) have the option to treat the contract as having been terminated with from the time of the fraudulent act and, if chosen the option, be entitled to refuse all claims arising after the fraud, but (3) remain liable for legitimate losses before the fraudulent act. LC is not recommending a complete restatement of the law on insurance fraud generally. For example, LC does not seek to define fraud, instead, recommends the introduction of targeted provisions to confirm the remedies available to an insurer who discovers a fraud by a policyholder.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2017년도 제55차 동계학술대회논문집 25권1호
• /
• pp.103-104
• /
• 2017

최근들어 보험사기로 인한 피해가 날로 극심해지고 있다. 이러한 보험사기로 인한 피해를 예방하고 억제하기 위해 오랜시간 논의를 해왔으며, 결국 보험사기방지 특별법을 제정하여 2016. 9. 30. 시행하였다. 그러나 단지 이러한 특별법 시행만으로는 보험사기로 인한 폐해를 완전히 해결할 수 없다. 따라서 특별법 시행으로 인한 현실적인 보험사기 억제효과를 살펴보고 이에 대한 문제점을 분석하여야 한다. 이에 본 연구에서는 보험사기방지 특별법 시행으로 인한 효과에 대하여 현실적으로 살펴보고, 이에 대한 문제점을 모색한 후 개선방안을 제시해 보고자 한다.

• 보건행정학회지
• /
• 제28권2호
• /
• pp.186-193
• /
• 2018

Background: The aim of our study was to review the findings of health insurance fraud investigations and to evaluate their impacts on medical costs for target and non-target organizations. An interrupted time series study design using generalized estimation equations was used to evaluate changes in cost following fraud investigations. Methods: We used National Health Insurance claims data from 2009 to 2015, which included 20,625 medical institutions (1,614 target organizations and 19,011 non-target organizations). Outcome variable included cost change after fraud investigation. Results: Following the initiation of fraud investigations, we found statistically significant reductions in cost level for target organizations (-1.40%, p<0.001). In addition, a reduction in cost trend change per month was found for both target organizations and non-target organizations after fraud investigation (target organizations, -0.33%; non-target organizations of same region, -0.19%; non-target organizations of other regions, -0.17%). Conclusion: This study suggested that fraud investigations are associated with cost reduction in target organization. We also found similar effects of fraud investigations on health expenditure for non-target organizations located in the same region and in different regions. Our finding suggests that fraud investigations are important in controlling the growth of health expenditure. To maximize the effects of fraud investigation on the growth of health expenditure, more organizations needed to be considered as target organizations.

• 한국자동차공학회논문집
• /
• 제21권6호
• /
• pp.58-63
• /
• 2013

It is very difficult to evaluate the impact speed, who caused the accident and what the injury risk of the vehicle occupants was from the outcome of the accident. That's the main reason why there are so many insurance fraud related to vehicle accident. In this study, a vehicle crash accident suspected to an insurance fraud had been reconstructed to evaluate crash speed and the relationship between the crash accident and passenger injury risk. To do this, the scene was reconstructed based on accident investigation report and three vehicle crash tests were done at 27kph, 37kph and 70kph. The crash speed of 27kph and 37kph were chosen based on the damaged vehicle and 70kph was chosen based on the driver's statement. Based on the damage of vehicle and dummy injury measure, impact speed is estimated around 20 to 30kph and the dummy measures show that the passengers are not seems to be severely injured in this speed range.